Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/antonbabenko/deliberation/claude-mdgit clone --depth 1 https://github.com/antonbabenko/deliberationWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.07547 | $0.07547 |
| Opus 5 | $0.03773 | $0.03773 |
| Sonnet 5 | $0.01509 | $0.01509 |
| Haiku 4.5 | $0.00755 | $0.00755 |
Grade B, and why
deliberation CLAUDE.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **`analyze` tool** (`core/analyze.js` + `commands/analyze.md`) - reads the debug log back (tail-bounded, pre-aggregated server-side) for per-model latency/tokens/error/effort (Lens A) and the session store for verdict How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
A Claude Code plugin that provides GPT (via Codex CLI), Gemini 3 (via the Antigravity CLI agy), Grok (via the xAI HTTP API), and OpenRouter (config-driven, advisory-only, 400+ models) as specialized expert subagents. Seven domain experts that can advise OR implement: Architect, Plan Reviewer, Scope Analyst, Code Reviewer, Security Analyst, Researcher, and Debugger. (Grok and OpenRouter are advisory-only - they cannot edit files. Grok reads attached files via the xAI Files API; OpenRouter inlines text files only.)
Development Commands
# Test plugin locally (loads from working directory)
claude --plugin-dir /path/to/deliberation
# Run setup to test installation flow
/deliberation:setup
# Run uninstall to test removal flow
/deliberation:uninstall
No build step, no dependencies. Codex exposes a native MCP server; Gemini, Grok, and OpenRouter use bundled zero-dependency Node bridges (server/gemini/index.js, server/grok/index.js, server/openrouter/index.js). The Gemini bridge wraps the Antigravity CLI (agy) in print mode. The OpenRouter bridge calls any OpenAI-compatible /chat/completions endpoint.
Architecture
Repository layout
core/- host-neutral, zero runtime deps, strict-typed. Provider interface +toErrorResult+ the opinion schema/envelope (types.js/provider.js):OPINION_SCHEMA(recommendation+confidenceenum + optionaldissent_points/assumptions/tradeoffsstring[]),parseOpinion(text) -> OpinionEnvelope(best-effort, never throws;structured= parse provenance), advisoryvalidateOpinion({valid, wellFormed, warnings}),OPINION_INSTRUCTIONS, andparseReview(text) -> {verdict, criticalIssues}(best-effort, never-throws: fenced-code-skipped verdict ladder -VERDICT:sentinel / same-line keyword /Verdictheading-split / bare token - plus the closed 6-category taxonomy with next-line continuation-join) used by the convergence loop.registry.js(selectForAskAll/selectForConsensus);orchestrate.js(askAll/askOne/consensus/runToConvergence- the non-Claude server-side loop driver);consensus-loop.js(the PURE convergence state machine - the SSOT for round counting, the convergence rule, the configurable max-rounds cap, history, and the confidence label);loop-store.js(ephemeral sliding-TTL + LRUMapholdingLoopStateacross the statelessconsensus-stepcalls; independent ofsessions.persist);providers/*.jsadapters (codex.jsspawns the Codex CLI;antigravity.js/grok.js/openai-compatible.jswrap their bridge via an injectableopts.bridge);paths.js(config + cache path resolver,DELIBERATION_CONFIGoverride).server/mcp/- stdio JSON-RPC MCP server overcore. Published as@antonbabenko/deliberation-mcp: an esbuildprepackstep bundlescore+ the three bridges into a self-containeddist/index.js(build-time devDep only;dist/gitignored).server.jsonat the repo root is the Official MCP Registry manifest.server/{gemini,grok,openrouter}/- the provider bridges (gemini wraps theagyCLI; grok = xAI HTTP; openrouter = any OpenAI-compatible HTTP) plus openrouterconfig.js(validateConfig/makeConfigReader, the config SSOT). Registered (with the unifiedserver/mcpserver) inline in.claude-plugin/plugin.jsonunder themcpServerskey (deliberation-*/deliberation) - this inline block is the SOLE runtime MCP registration. Claude Code reads MCP servers from a plugin's root.mcp.jsonOR inline inplugin.json; the inline form is used so the manifest is NOT also auto-loaded as a project-scope.mcp.jsonwhen working inside this repo (which would duplicate every server with an unresolved${CLAUDE_PLUGIN_ROOT}). The args use${CLAUDE_PLUGIN_ROOT}, which Claude Code resolves to the installed version on every load, so updating is just/plugin marketplace update antonbabenko+/reload-plugins./deliberation:setupseeds config and installs rules; it does not register MCP servers.- Typecheck gate -
tsconfig.jsonstrictcheckJsovercore/**+server/mcp/**/*.js(excludesserver/mcp/dist).npm run check=typecheck+node --test test/*.test.js, enforced in CI by.github/workflows/validate.yml.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 265 lines · 7,547 tokens per session scan B e489884220ef
deliberation CLAUDE.md is an instructions file published in the GitHub repository antonbabenko/deliberation (138 stars, last pushed 5d ago), licensed MIT. It adds 7,547 tokens to every session, about $0.0377 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
ima2-gen AGENTS.md
Instructions for lidge-jun/ima2-gen, covering ima2-gen — ai context, what this project does, tech stack, project structure and agent skills (packaged).
bob-plugin-ollama-translator AGENTS.md
Instructions for CaicoLeung/bob-plugin-ollama-translator, covering repository guidelines, project overview, architecture & data flow, key directories and development commands.
bob-plugin-ollama-translator CLAUDE.md
Instructions for CaicoLeung/bob-plugin-ollama-translator, covering claude.md, agent skills, issue tracker, triage labels and domain docs.
ThreadShelf AGENTS.md
Instructions for ChrystianSchutz/ThreadShelf, covering agents.md, what this project is, repository layout, commands and conventions.
deep-research AGENTS.md
Instructions for u14app/deep-research, covering agents.md, 🚀 development workflow & commands, core commands, testing and 📂 project structure.
EleSync copilot-instructions.md
When working on the EleSync repository, prefer the EleSync Maintainer custom agent for Python code, docs, tests, packaging, and release workflow changes.